Kimi K3
Moonshot AI · text, image, video → text
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.
Input$3.00 /M
Output$15.00 /M
← ModelsKimi K3
Qwen Mt Turbo
Kimi K3 vs Qwen Mt Turbo
Output tokens cost $15.00 per million on Kimi K3 and $0.53 per million on Qwen Mt Turbo. Input tokens cost $3.00 per million on Kimi K3 and $0.19 per million on Qwen Mt Turbo. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.19 per million on Qwen Mt Turbo. Context lengths are 1,048,576 tokens on Kimi K3 and 16,000 tokens on Qwen Mt Turbo. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 0.9s on Qwen Mt Turbo. Measured output throughput is 73.1 tok/s on Kimi K3 and 3.4 tok/s on Qwen Mt Turbo.
Kimi K3Qwen Mt Turbo+ Add model · 2/4
Qwen Mt Turbo
Qwen · text → text
Based on the comprehensive upgrade of Qwen3, this flagship translation large model supports bidirectional translation across 92 languages. It offers fully enhanced model performance and translation quality, along with more stable terminology customization, format fidelity, and domain-prompting capabilities, making translations more accurate and natural.
Input$0.19 /M
Output$0.53 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen Mt Turbo
Input /M
$3.00
$0.19
Output /M
$15.00
$0.53
Cache read /M
$0.30
$0.19
Context length
1,048,576
16,000
Max output
1,048,576
8,000
Time to First Token
0.9 s
0.9 s
Throughput
73.1 tok/s
3.4 tok/s
Modalities
textimagevideo
text
Supported Parameters
thinkingfunction callingstructured outputs
API Formats
Released
-
-
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
kimi-k3qwen-mt-turbo
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen-mt-turbo
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
Qwen Mt Turbo
$19.54 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen Mt Turbo?
Qwen Mt Turbo: $0.53/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
Qwen Mt Turbo: 0.9s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
Kimi K3 accepts 1,048,576 and Qwen Mt Turbo accepts 16,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 8,000 tokens on Qwen Mt Turbo.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Qwen Mt Turbo at 3.4 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs; Qwen Mt Turbo accepts text input.
Can I call Kimi K3 and Qwen Mt Turbo with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
AIHubMix